Optimal Embedding Guided Negative Sample Generation for Knowledge Graph Link Prediction

2025-04-04

AI Summary

In knowledge graph link prediction, low-quality negative samples severely hinder the performance of embedding models. To address this, we propose EMU, a novel framework that theoretically derives a sufficient condition for the effectiveness of negative sample distributions. EMU shifts from conventional sampling to a *generative* negative sampling paradigm: guided by optimal embedding conditions, it actively constructs negative triples via embedding perturbations—including directional disturbance and norm scaling—that provably satisfy theoretical optimality. EMU is model-agnostic and seamlessly integrates with any knowledge graph embedding (KGE) model (e.g., TransE, ComplEx, RotatE) and existing sampling strategies, supporting end-to-end joint training. Extensive experiments on standard benchmarks (FB15k-237, WN18RR) demonstrate significant improvements in MRR and Hits@1—equivalent to increasing embedding dimensionality fivefold. The code is publicly available.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Knowledge graph embedding (KGE) models encode the structural information of knowledge graphs to predicting new links. Effective training of these models requires distinguishing between positive and negative samples with high precision. Although prior research has shown that improving the quality of negative samples can significantly enhance model accuracy, identifying high-quality negative samples remains a challenging problem. This paper theoretically investigates the condition under which negative samples lead to optimal KG embedding and identifies a sufficient condition for an effective negative sample distribution. Based on this theoretical foundation, we propose extbf{E}mbedding extbf{MU}tation ( extsc{EMU}), a novel framework that emph{generates} negative samples satisfying this condition, in contrast to conventional methods that focus on emph{identifying} challenging negative samples within the training data. Importantly, the simplicity of extsc{EMU} ensures seamless integration with existing KGE models and negative sampling methods. To evaluate its efficacy, we conducted comprehensive experiments across multiple datasets. The results consistently demonstrate significant improvements in link prediction performance across various KGE models and negative sampling methods. Notably, extsc{EMU} enables performance improvements comparable to those achieved by models with embedding dimension five times larger. An implementation of the method and experiments are available at https://github.com/nec-research/EMU-KG.

Problem

• Improving negative sample quality for knowledge graph link prediction
• Theoretical conditions for optimal negative sample distribution
• Generating high-quality negative samples via Embedding Mutation (EMU)

Innovation

• Proposes Embedding Mutation (EMU) framework
• Generates optimal negative samples theoretically
• Seamlessly integrates with existing KGE models